Training in progress, epoch 1

config.json

@@ -1,30 +1,54 @@
 {
-  "_name_or_path": "facebook/deit-base-patch16-224",
+  "_name_or_path": "microsoft/swin-base-patch4-window7-224-in22k",
   "architectures": [
-    "ViTForImageClassification"
+    "SwinForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "encoder_stride": 16,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 128,
+  "encoder_stride": 32,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0"
   },
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 12,
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
   "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 16,
+  "num_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "num_layers": 4,
+  "out_features": null,
+  "patch_size": 4,
+  "path_norm": true,
   "problem_type": "multi_label_classification",
   "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.26.0"
+  "transformers_version": "4.26.0",
+  "use_absolute_embeddings": false,
+  "window_size": 7
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f8c0e351e92c8e9c15190fee525acae1220436f04ea18c798fda20f904ba49
-size 343265645
+oid sha256:e75fd4c6472f0124c9781ddc82ba32d0e663bd023328ad31c1d764375a3d2756
+size 347595665

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ce2bbea69496608b4ca542f74718b6fdaaefe4c1e444975714399ec6356dc4
+oid sha256:c39aae2fef45e9f39e535da67ff162e972ec6a1dff04fcf014a47c15b1f8d9b2
 size 3515